list_project_custom_fields
AI agents call list_project_custom_fields to retrieve information from Clockify Time Tracking without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves or queries custom field metadata for projects. This is a retrieval operation (Read category) with minimal severity—it only accesses configuration data that would not cause harm if misused. Confidence is slightly reduced due to empty description, but the name strongly indicates a query operation.
From the tool's definition Tool name 'list_project_custom_fields' indicates retrieval of custom field definitions for projects. The verb 'list' is a query operation with no side effects.
Attacks that exploit this kind of access
list_project_custom_fields. It is categorised as a Read tool in the Clockify Time Tracking MCP Server, which means it retrieves data without modifying state.
Register the Clockify Time Tracking MCP server in PolicyLayer and add a rule for list_project_custom_fields: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Clockify Time Tracking. Nothing to install.
list_project_custom_fields is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_project_custom_fields rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_project_custom_fields. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_project_custom_fields is provided by the Clockify Time Tracking MCP server (pypi:clockify-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →